Triple
T9026363
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GameCube controller |
E216055
|
entity |
| Predicate | buttonLayout |
P84763
|
FINISHED |
| Object | large central A button |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: large central A button | Statement: [GameCube controller, buttonLayout, large central A button]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: buttonLayout Context triple: [GameCube controller, buttonLayout, large central A button]
-
A.
buttonPlacement
chosen
Indicates the spatial or positional arrangement of a button relative to other elements or within a given interface or context.
-
B.
controlLayout
Indicates that one entity determines or manages the spatial or structural arrangement of another entity.
-
C.
buttonType
Indicates the specific category or style of a button within a user interface or control set.
-
D.
crewLayout
Indicates how crew members are arranged or distributed within a vehicle, vessel, or structure.
-
E.
buttonGrouping
Indicates that multiple buttons are associated together as a single logical or functional group.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca83a5fa88819088144801b4dd7245 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6a7ce71c81908041814dc9ec1713 |
completed | April 1, 2026, 12:44 a.m. |
| PD | Predicate disambiguation | batch_69cc5ee132f08190940749c7c522e4c1 |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:07 p.m.